RAP-Net: Recurrent Attention Pooling Networks for Dialogue Response Selection. (September 2020)

• Record Type: Journal Article
• Authors: Huang, Chao-Wei; Chiang, Ting-Rui; Su, Shang-Yu; Chen, Yun-Nung
• Is Part Of: Computer speech & language. Volume 63(2020)
• Publication Date: 2020-09
• Subjects: Attention -- Dialogue modeling -- Response selection -- DSTC; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2020.101079
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: A novel framework estimates the relevance between dialogue contexts and responses. The RAP-Net model integrates benefits from recurrent units, attention, and pooling. The model is capable of generalize to different response selection datasets. The proposed knowledge-grounding feature significantly improves the results. Graphical abstract: Abstract: The response selection has been an emerging research topic due to the growing interest in dialogue modeling, where the goal of the task is to select an appropriate response for continuing dialogues. To further push the end-to-end dialogue model toward real-world scenarios, the seventh Dialog System Technology Challenge (DSTC7) proposed a challenge track based on real chatlog datasets. The competition focuses on dialogue modeling with several advanced characteristics: (1) natural language diversity, (2) capability of precisely selecting a proper response from a large set of candidates or the scenario without any correct answer, and (3) knowledge grounding. This paper introduces recurrent attention pooling networks (RAP-Net), a novel framework for response selection, which can well estimate the relevance between the dialogue contexts and the candidates. The proposed RAP-Net is shown to be effective and can be generalize across different datasets and settings in the DSTC7 experiments.